GenAI/Python Senior Engineer

Tata Consultancy Services; Anna (TX); On-site; USD 90,000 - 130,000; Full time

Benefits offered by this job

Discretionary Annual Incentive

Comprehensive Medical Coverage

Family Leave and Parental Benefits

401K Plan & Retirement Support

Certification & Training Reimbursement

Vacation & Holidays

Job summary

Tata Consultancy Services in Anna, Texas, is seeking a seasoned Python developer to build production-grade GenAI/LLM applications. You will implement agentic workflows, design JSON-based payload pipelines, and integrate semantic search with vector databases.

Collaboration with engineering and product teams is essential for delivering scalable, production-ready capabilities. Role emphasizes async orchestration, robust testing, and clear technical documentation.

Qualifications

• 5+ years of advanced Python development experience with production-grade practices.
• 1.5+ years building GenAI/LLM applications in production using model APIs.
• Experience building LLM-powered agents and multi-step orchestration.
• Strong experience with structured output extraction using JSON schema and validation logic.
• Proficiency in vector search, RAG, and semantic search concepts.
• API development with FastAPI or similar frameworks; async orchestration.

Responsibilities

• Build and enhance LLM-powered agentic applications in Python.
• Develop intent classification and agent workflows for complex questions.
• Create NL-to-structured payload pipelines (JSON queries) for filters and rankings.
• Integrate semantic search and vector retrieval for entity resolution and disambiguation.
• Design, build, and consume FastAPI-based microservices.
• Implement async orchestration for parallel LLM/API calls and services.
• Develop prompt engineering patterns, JSON validation, and guardrails.
• Create evaluation harnesses and regression tests for prompt/model changes.
• Collaborate across platform, data, service, and product teams; document decisions.

Skills

Python

GenAI

LLM development

FastAPI

JSON schema validation

Async Python

SQL

Git CI/CD

API orchestration

Tools

LangChain

Pinecone

Weaviate

OpenSearch

pgvector

Azure/AWS/GCP

LlamaIndex

Job description

Job Description

• 5+ years of advanced professional Python development experience with production-grade coding practices.
• Strong hands-on experience writing clean, tested, maintainable code using typing, pytest, packaging standards, Git, CI/CD, Docker, and code review discipline.
• 1.5+ years of hands-on experience building GenAI / LLM applications in production using OpenAI, Azure OpenAI, Anthropic, Bedrock, or similar model APIs.
• Experience building LLM-powered agents, including intent classification, domain-specific agents, agentic extraction flows, and multi-step orchestration.
• Hands-on experience with Agentic AI frameworks or patterns such as LangChain, LangGraph, LlamaIndex, function calling, tool use, or custom orchestration.
• Strong experience in structured output extraction from LLMs using JSON schema enforcement, Pydantic, retry/repair strategies, and validation logic.
• Experience with RAG and vector search concepts including embeddings, chunking, hybrid search, reranking, entity resolution, fuzzy matching, confidence thresholds, and disambiguation flows.
• Working knowledge of vector databases or search platforms such as pgvector, Pinecone, Weaviate, OpenSearch, Snowflake vector functions, or equivalent.
• Strong API development experience using FastAPI or similar frameworks such as Flask or Django.
• Experience with async Python and orchestration of parallel LLM/API calls.
• Strong SQL skills and comfort working with large analytical datasets.
• Cloud environment experience, preferably Azure; AWS or GCP acceptable.
• Strong written and verbal communication skills, with ability to collaborate directly with engineering teams, product owners, and cross-functional stakeholders.
• Build and enhance LLM-powered agentic applications using Python.
• Develop intent classification, domain-specialist agent workflows, and agentic extraction pipelines for complex user questions.
• Build natural-language-to-structured-payload pipelines that convert user utterances into accurate JSON query payloads, including filters, exclusions, rankings, and metric selection.
• Integrate semantic search and vector retrieval services for embedding-based entity resolution, fuzzy matching, confidence scoring, and disambiguation flows.
• Design, build, and consume FastAPI-based microservices.
• Implement async orchestration patterns for parallel LLM calls, API calls, and downstream service integrations.
• Develop prompt engineering patterns, structured output enforcement, JSON schema validation, function calling, tool usage, and guardrails.
• Build evaluation harnesses, test sets, and regression test frameworks to measure extraction accuracy and validate prompt/model changes.
• Work with metadata/catalog services, entitlement-aware data access, and reporting-engine payload contracts.
• Collaborate with multiple platform, data, service, and product teams to deliver production-ready GenAI capabilities.
• Write clear technical documentation including Confluence pages, ADRs, sequence diagrams, and flow diagrams.
• Participate in hands-on technical evaluation, code reviews, design discussions, and production readiness reviews.

Must Have Technical/Functional Skills

• 5+ years of advanced professional Python development experience with production-grade coding practices.
• Strong hands-on experience writing clean, tested, maintainable code using typing, pytest, packaging standards, Git, CI/CD, Docker, and code review discipline.
• 1.5+ years of hands-on experience building GenAI / LLM applications in production using OpenAI, Azure OpenAI, Anthropic, Bedrock, or similar model APIs.
• Experience building LLM-powered agents, including intent classification, domain-specific agents, agentic extraction flows, and multi-step orchestration.
• Hands-on experience with Agentic AI frameworks or patterns such as LangChain, LangGraph, LlamaIndex, function calling, tool use, or custom orchestration.
• Strong experience in structured output extraction from LLMs using JSON schema enforcement, Pydantic, retry/repair strategies, and validation logic.
• Experience with RAG and vector search concepts including embeddings, chunking, hybrid search, reranking, entity resolution, fuzzy matching, confidence thresholds, and disambiguation flows.
• Working knowledge of vector databases or search platforms such as pgvector, Pinecone, Weaviate, OpenSearch, Snowflake vector functions, or equivalent.
• Strong API development experience using FastAPI or similar frameworks such as Flask or Django.
• Experience with async Python and orchestration of parallel LLM/API calls.
• Strong SQL skills and comfort working with large analytical datasets.
• Cloud environment experience, preferably Azure; AWS or GCP acceptable.
• Strong written and verbal communication skills, with ability to collaborate directly with engineering teams, product owners, and cross-functional stakeholders.

Roles & Responsibilities

• Build and enhance LLM-powered agentic applications using Python.
• Develop intent classification, domain-specialist agent workflows, and agentic extraction pipelines for complex user questions.
• Build natural-language-to-structured-payload pipelines that convert user utterances into accurate JSON query payloads, including filters, exclusions, rankings, and metric selection.
• Integrate semantic search and vector retrieval services for embedding-based entity resolution, fuzzy matching, confidence scoring, and disambiguation flows.
• Design, build, and consume FastAPI-based microservices.
• Implement async orchestration patterns for parallel LLM calls, API calls, and downstream service integrations.
• Develop prompt engineering patterns, structured output enforcement, JSON schema validation, function calling, tool usage, and guardrails.
• Build evaluation harnesses, test sets, and regression test frameworks to measure extraction accuracy and validate prompt/model changes.
• Work with metadata/catalog services, entitlement-aware data access, and reporting-engine payload contracts.
• Collaborate with multiple platform, data, service, and product teams to deliver production-ready GenAI capabilities.
• Write clear technical documentation including Confluence pages, ADRs, sequence diagrams, and flow diagrams.
• Participate in hands-on technical evaluation, code reviews, design discussions, and production readiness reviews.

Salary Range-$90,000-$130,000 a year

TCS Employee Benefits Summary

• Discretionary Annual Incen tive.
• Comprehensive Medical Coverage: Medical & Health, Dental & Vision, Disability Planning & Insurance, Pet Insurance Plans.
• Family Support: Maternal & Parental Leaves.
• Insurance Options: Auto & Home Insurance, Identity Theft Protection.
• Convenience & Professional Growth: Commuter Benefits & Certification & Training Reimbursement.
• Time Off: Vacation, Time Off, Sick Leave & Holidays.
• Legal & Financial Assistance: Legal Assistance, 401K Plan, Performance Bonus, College Fund, Student Loan Refinancing.