Description

Key Responsibilities

- Design, build, and deploy enterprise-grade GenAI applications using LLMs and agentic architectures.
- Develop end-to-end RAG pipelines covering:
- Document ingestion
- Parsing and extraction
- Embedding generation
- Retrieval optimization
- Response generation

- Build scalable ingestion frameworks for:

- PDF
- DOCX
- PPT
- Images and scanned documents

- Implement semantic search solutions using vector databases and hybrid retrieval approaches.
- Design and deploy multi-agent workflows using frameworks such as:

- LangGraph
- LangChain
- CrewAI

- Develop backend services and orchestration layers using FastAPI and Python.
- Integrate foundation models through:

- Azure OpenAI
- AWS Bedrock
- OpenAI APIs
- Anthropic Claude
- Llama models

- Optimize AI solutions for:

- Accuracy
- Latency
- Cost efficiency
- Reliability

- Implement evaluation and observability frameworks using:

- LangSmith
- LangFuse
- RAGAS
- DeepEval

Collaborate with business teams to integrate AI capabilities into enterprise applications and workflows.

Enable Skills-Based Hiring No ECMS REQ IDAdditional Details

- ECMS REQ ID : 584210
- Project Location 1 : Pan India
- Project Location 2 : (No Value)
- Project Location 3 : (No Value)
- Project Location 4 : (No Value)
- Delivery SPOC : Nishit Kumar
- Relevant Experience : 6+ Yrs
- Mandatory skills : Programming• Advanced Python development• Experience working within large enterprise codebases• Strong software engineering and API design fundamentalsGenAI & LLMs• Hands-on experience with:



o GPT serieso Claudeo Llamao Other foundation models• Prompt engineering and context management• Embeddings and vector search• RAG architecture design• Agentic AI systemsFrameworks• LangChain• LangGraph• CrewAI• FastAPICloud & Infrastructure• AWS Preferred: o Bedrocko S3o ECS/Fargateo Lambdao API Gateway• Azure AI Studio experience is a plusDatabases• Vector databases such as: o Pineconeo Weaviateo Chromao OpenSearch Vector Searcho Databricks Vector SearchDevOps• Docker• GitHub Actions• CI/CD for AI applications
- Desired skills : Programming• Advanced Python development• Experience working within large enterprise codebases• Solid software engineering and API design fundamentalsGenAI & LLMs• Hands-on experience with: o GPT serieso Claudeo Llamao Other foundation models• Prompt engineering and context management• Embeddings and vector search• RAG architecture design• Agentic AI systemsFrameworks• LangChain• LangGraph• CrewAI• FastAPICloud & Infrastructure• AWS Preferred: o Bedrocko S3o ECS/Fargateo Lambdao API Gateway• Azure AI Studio experience is a plusDatabases• Vector databases such as: o Pineconeo Weaviateo Chromao OpenSearch Vector Searcho Databricks Vector SearchDevOps• Docker• GitHub Actions• CI/CD for AI applications
- Domain (Industry) : Oil and Gas
- BGC (Before onboarding / After onboarding) : PreOB
- Total Experience (Ex. 5-7 Years) : 6+ Yrs
- BGC Details : Standard Infosys checklist
- BGC Vendor : Any NASSCOM Vendor
- Mode of Interview : Face to Face
- WFO / WFH / Hybrid : Hybrid
- Please enter shift timings : UK Shift
- Shift Timings : Afternoon

📌 584210 | IC | AI Engineer | INDIA
🏢 Trigent Software
📍 India