Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m an AI software engineer with 3+ years of experience building and deploying production-grade enterprise AI systems, including LLM-powered copilots, agentic workflows, and retrieval-augmented knowledge assistants. I specialize in RAG and GraphRAG, semantic search, and multi-agent orchestration using frameworks like LangChain, LangGraph, LlamaIndex, and CrewAI, with a strong focus on grounding, structured outputs, and tool/function calling. In my work, I design scalable AI microservices and distributed inference platforms across AWS, Azure, and Google Cloud, optimizing for latency, throughput, and reliability. I also build end-to-end MLOps/LLMOps pipelines with observability and evaluation (MLflow, LangSmith, Langfuse, OpenTelemetry, Grafana, RAGAS) and partner with product and platform teams to deliver secure, measurable solutions such as service desk automation, incident resolution, and knowledge intelligence that improve routing accuracy and reduce resolution time.…I’m an AI software engineer with 3+ years of experience building and deploying production-grade enterprise AI systems, including LLM-powered copilots, agentic workflows, and retrieval-augmented knowledge assistants. I specialize in RAG and GraphRAG, semantic search, and multi-agent orchestration using frameworks like LangChain, LangGraph, LlamaIndex, and CrewAI, with a strong focus on grounding, structured outputs, and tool/function calling. In my work, I design scalable AI microservices and distributed inference platforms across AWS, Azure, and Google Cloud, optimizing for latency, throughput, and reliability. I also build end-to-end MLOps/LLMOps pipelines with observability and evaluation (MLflow, LangSmith, Langfuse, OpenTelemetry, Grafana, RAGAS) and partner with product and platform teams to deliver secure, measurable solutions such as service desk automation, incident resolution, and knowledge intelligence that improve routing accuracy and reduce resolution time.

Prem Akhil Boda

AI Developer, Full Stack Developer, Back-End Developer, +7





I’m an AI software engineer with 3+ years of experience building and deploying production-grade enterprise AI systems, including LLM-powered copilots, agentic workflows, and retrieval-augmented knowledge assistants. I specialize in RAG and GraphRAG, semantic search, and multi-agent orchestration using frameworks like LangChain, LangGraph, LlamaIndex, and CrewAI, with a strong focus on grounding, structured outputs, and tool/function calling. In my work, I design scalable AI microservices and distributed inference platforms across AWS, Azure, and Google Cloud, optimizing for latency, throughput, and reliability. I also build end-to-end MLOps/LLMOps pipelines with observability and evaluation (MLflow, LangSmith, Langfuse, OpenTelemetry, Grafana, RAGAS) and partner with product and platform teams to deliver secure, measurable solutions such as service desk automation, incident resolution, and knowledge intelligence that improve routing accuracy and reduce resolution time.…I’m an AI software engineer with 3+ years of experience building and deploying production-grade enterprise AI systems, including LLM-powered copilots, agentic workflows, and retrieval-augmented knowledge assistants. I specialize in RAG and GraphRAG, semantic search, and multi-agent orchestration using frameworks like LangChain, LangGraph, LlamaIndex, and CrewAI, with a strong focus on grounding, structured outputs, and tool/function calling. In my work, I design scalable AI microservices and distributed inference platforms across AWS, Azure, and Google Cloud, optimizing for latency, throughput, and reliability. I also build end-to-end MLOps/LLMOps pipelines with observability and evaluation (MLflow, LangSmith, Langfuse, OpenTelemetry, Grafana, RAGAS) and partner with product and platform teams to deliver secure, measurable solutions such as service desk automation, incident resolution, and knowledge intelligence that improve routing accuracy and reduce resolution time.

Available to hire

I’m an AI software engineer with 3+ years of experience building and deploying production-grade enterprise AI systems, including LLM-powered copilots, agentic workflows, and retrieval-augmented knowledge assistants. I specialize in RAG and GraphRAG, semantic search, and multi-agent orchestration using frameworks like LangChain, LangGraph, LlamaIndex, and CrewAI, with a strong focus on grounding, structured outputs, and tool/function calling.

In my work, I design scalable AI microservices and distributed inference platforms across AWS, Azure, and Google Cloud, optimizing for latency, throughput, and reliability. I also build end-to-end MLOps/LLMOps pipelines with observability and evaluation (MLflow, LangSmith, Langfuse, OpenTelemetry, Grafana, RAGAS) and partner with product and platform teams to deliver secure, measurable solutions such as service desk automation, incident resolution, and knowledge intelligence that improve routing accuracy and reduce resolution time.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Beginner

Beginner

Beginner

Beginner

Language

English

Fluent

Work Experience

AI Software Engineer at DoorDash

May 1, 2025 - Present

Architected enterprise-grade AI agents and conversational copilots using Python and LLM APIs (OpenAI, Anthropic, plus Llama/Mistral), implementing prompt/structured output, function calling, and tool calling to automate employee support, ITSM, and business workflows. Engineered high-throughput inference and model-serving using TGI/vLLM, Kubernetes, and AWS/Azure services, optimizing latency, throughput, and cost for large-scale RAG and agentic workloads under production SLAs. Orchestrated multi-agent execution with LangGraph/CrewAI/AutoGen and MCP, including ReAct patterns, agent memory, workflow planning, and autonomous task execution. Built knowledge intelligence systems using GraphRAG with vector stores and hybrid retrieval (Pinecone/Weaviate/FAISS/OpenSearch), including ingestion, chunking, embeddings, reranking, and semantic search for improved grounding and response accuracy. Delivered AI-powered service desk/incident resolution integrating ServiceNow/Jira/Teams/Salesforce, impro

AI-Software Engineer at DoorDash

May 1, 2025 - Present

Architected enterprise-grade AI agents and conversational copilots using Python, OpenAI API, Anthropic Claude API, Llama, and Mistral models; implementing prompt engineering, structured output generation, function calling, and tool calling frameworks to automate employee support, ITSM, and business workflow operations. Engineered high-throughput AI inference and model-serving platforms using TGI, vLLM, Kubernetes, AWS EC2, S3, and Azure cloud services. Orchestrated multi-agent execution frameworks leveraging LangGraph, CrewAI, AutoGen, and MCP, implementing ReAct reasoning patterns, memory architectures, and autonomous task execution for complex enterprise process automation. Constructed GraphRAG-based knowledge platforms with Pinecone, Weaviate, FAISS, OpenSearch, and hybrid retrieval strategies. Delivered AI-powered service desk and incident resolution capabilities integrating ServiceNow, Jira, Teams, Salesforce, and enterprise APIs, achieving 88%+ ticket routing accuracy and a 35% r

Machine Learning Engineer at Mphasis

September 1, 2022 - November 30, 2023

Refactored experimental Python-based ML prototypes into modular, production-ready applications using object-oriented programming, asyncio, Pydantic, and software engineering best practices. Automated end-to-end ML pipelines with Apache Airflow and GitHub Actions, reducing manual intervention by ~40%. Deployed real-time and batch inference solutions on AWS SageMaker, Azure ML, and Kubernetes (Docker/Terraform) with sub-100ms latency and 99.9% production availability for fraud detection, risk scoring, and predictive analytics. Established MLOps frameworks (MLflow, Weights & Biases, Jenkins) for experiment tracking, model versioning, automated testing, continuous training, and release management. Implemented NLP and intelligent document processing using Python, Hugging Face Transformers, BERT, SpaCy, OCR pipelines to automate classification and information extraction. Built enterprise knowledge retrieval and customer support automation using LangChain, LlamaIndex, vector databases (Pineco

Software Developer at KPIT Technologies

July 1, 2021 - August 31, 2022

Created and maintained automotive software modules using Python, C++, and JavaScript for connected vehicle and telematics platforms; contributed to ECU software integration, vehicle communication workflows (REST, CAN), and diagnostic support tools. Optimized PostgreSQL, MySQL, Redis, and NoSQL databases for telemetry ingestion and analytics, achieving improved response times. Instituted DevSecOps and quality engineering across pipelines, reducing regression defects by ~30%. Enhanced NLP and semantic search capabilities with FAISS-powered retrieval to improve fault classification and root-cause analysis, supporting diagnostics workflows. Supported validation activities in Agile/Scrum environments, leveraging modern developer productivity tools (GitHub Copilot, Cursor) to improve delivery efficiency and code quality.