Production GenAI Platform on AWS
Budget: ₹12,500 – ₹37,500 INR
I’m taking a proof-of-concept Generative AI system into full production and want a senior engineer who has already solved the real-world problems this move uncovers. The stack is centred on Amazon Bedrock, where we are actively working with Claude 3, Titan, Llama 3 and Mistral. Your track record should show that you have wired those or comparable foundation models into live workloads before.
Our orchestration layer relies on LangChain working hand-in-hand with LlamaIndex, Bedrock Agents and a set of custom integrations, so fluency with that trio is essential. Everything is written in modern Python (3.9+), surfaced through API Gateway, executed in Lambda and coordinated with Step Functions. Vector databases drive our semantic search, while Glue and Athena sit behind a serverless ETL pipeline that ingests both structured and unstructured data at scale.
The contract runs for 12 months, fully remote, operating primarily on the IST time zone. Day-to-day you will:
• Extend and maintain the Bedrock integrations and embeddings workflow
• Design fault-tolerant ETL jobs in Glue, optimised for Athena queries
• Tune vector search and retrieval strategies for latency and relevance
• Harden our API layer for external consumption, including auth and rate limits
• Contribute clean, well-tested Python code and clear documentation
If you have 5 + years in AWS data engineering or adjacent roles, can demonstrate shipped work that combines Bedrock with LangChain/LlamaIndex, and are available to start straight away, I’d love to see your portfolio or a concise case study of a similar build.
We are ready to onboard immediately and will move quickly for the right person.
Our orchestration layer relies on LangChain working hand-in-hand with LlamaIndex, Bedrock Agents and a set of custom integrations, so fluency with that trio is essential. Everything is written in modern Python (3.9+), surfaced through API Gateway, executed in Lambda and coordinated with Step Functions. Vector databases drive our semantic search, while Glue and Athena sit behind a serverless ETL pipeline that ingests both structured and unstructured data at scale.
The contract runs for 12 months, fully remote, operating primarily on the IST time zone. Day-to-day you will:
• Extend and maintain the Bedrock integrations and embeddings workflow
• Design fault-tolerant ETL jobs in Glue, optimised for Athena queries
• Tune vector search and retrieval strategies for latency and relevance
• Harden our API layer for external consumption, including auth and rate limits
• Contribute clean, well-tested Python code and clear documentation
If you have 5 + years in AWS data engineering or adjacent roles, can demonstrate shipped work that combines Bedrock with LangChain/LlamaIndex, and are available to start straight away, I’d love to see your portfolio or a concise case study of a similar build.
We are ready to onboard immediately and will move quickly for the right person.