Senior Forward Deployed Engineer

Tata Consultancy Services; Owings Mills (MD); On-site; USD 130,000 - 150,000; Full time

Benefits offered by this job

Discretionary Annual Incentive

Comprehensive Medical Coverage

401K Plan

Certification & Training Reimbursement

Job summary

Tata Consultancy Services in Owings Mills, MD, is seeking a senior AI/GenAI engineer to lead end-to-end delivery of Claude-based AI and LLM solutions on AWS for enterprise platforms. The role emphasizes prototyping to production, collaboration with business users, and maintaining governance and security in complex environments.

You will design agent workflows, integrate APIs, and guide teams through MVPs to production, ensuring scalable, cost-effective AI deployments aligned with enterprise

Qualifications

• 12+ years of software/data engineering delivering AI/GenAI/LLM/RAG solutions.
• Claude-based AI solutions on Amazon Bedrock experience.
• Production API development with FastAPI/Flask.
• Agentic orchestration patterns with LangChain/LangGraph/LlamaIndex/AutoGen.

Responsibilities

• Lead hands-on build and productionization of Claude-based AI on AWS and enterprise platforms.
• Partner with business users to translate ambiguous needs into AI products.
• Own solution design for agent workflows, API/tool integrations and prompts.
• Drive rapid discovery, MVP delivery and production hardening for asset management use cases.
• Provide technical leadership through design/code reviews and governance.
• Integrate AI apps with internal systems and data sources.
• Troubleshoot live issues and optimize performance, latency and cost.

Skills

AI/ML engineering

Python

Cloud AI on AWS

LangChain

End-to-end delivery

Education

Bachelor’s in CS

Tools

FastAPI

Flask

LangChain

LlamaIndex

Bedrock

AWS

S3

API Gateway

Step Functions

Job description

• 12+ years of software/data engineering experience with strong hands‑on delivery of AI, GenAI, LLM, RAG and agentic AI solutions in enterprise environments.
• Proven experience leading prototype-to-production delivery of Claude based AI solutions, preferably using Anthropic Claude on Amazon Bedrock.
• Strong Python engineering skills with production API development experience using FastAPI, Flask or similar frameworks.
• Hands‑on experience with agentic orchestration patterns and frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen or similar.
• Deep experience with RAG pipelines, embeddings, vector databases, semantic search, document ingestion, re‑ranking, grounding and LLM evaluation.
• Strong AWS implementation experience across Bedrock, Lambda, API Gateway, Step Functions, ECS/EKS, S3, IAM, KMS, CloudWatch, CloudTrail and CI/CD.
• Experience integrating AI solutions with enterprise APIs, data platforms, workflow platforms, knowledge repositories and in‑house capabilities.
• Strong understanding of tool/function calling, MCP servers, guardrails, validation, human‑in‑the‑loop patterns, observability, latency and cost optimization.
• Functional exposure to Asset Management, Investment Operations, Distribution, Client Reporting or Middle Office processes is preferred.
• Lead hands‑on build, deployment and productionization of Claude based agentic AI, RAG and LLM solutions on AWS and enterprise internal platforms.
• Partner directly with business users, domain SMEs, architects, security, cloud and data teams to convert ambiguous needs into working AI products.
• Own solution design for agent workflows, API/tool integrations, prompt templates, evaluators, guardrails, human approval flows and exception handling.
• Drive rapid discovery, prototyping, MVP delivery, production hardening and scale‑up across prioritized asset management use cases.
• Provide technical leadership to FDEs and engineers through design reviews, code reviews, troubleshooting, reusable patterns and delivery governance.
• Integrate AI applications with internal systems, enterprise data sources, knowledge repositories, workflow tools and API ecosystems.
• Troubleshoot complex live issues including hallucination, retrieval quality, model behavior, latency, failed tool calls, orchestration errors and access constraints.
• Optimize performance, reliability and cost using caching, model routing, batching, prompt tuning, monitoring and architecture improvements.
• Ensure solutions align with enterprise security, IAM, encryption, audit logging, privacy, AI governance and model risk requirements.
• Create technical documentation, implementation plans, deployment runbooks, demos and transition materials for support and long‑term adoption.

Job Description

Must Have Technical/Functional Skills

• 12+ years of software/data engineering experience with strong hands‑on delivery of AI, GenAI, LLM, RAG and agentic AI solutions in enterprise environments.
• Proven experience leading prototype‑to‑production delivery of Claude based AI solutions, preferably using Anthropic Claude on Amazon Bedrock.
• Strong Python engineering skills with production API development experience using FastAPI, Flask or similar frameworks.
• Hands‑on experience with agentic orchestration patterns and frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen or similar.
• Deep experience with RAG pipelines, embeddings, vector databases, semantic search, document ingestion, re‑ranking, grounding and LLM evaluation.
• Strong AWS implementation experience across Bedrock, Lambda, API Gateway, Step Functions, ECS/EKS, S3, IAM, KMS, CloudWatch, CloudTrail and CI/CD.
• Experience integrating AI solutions with enterprise APIs, data platforms, workflow platforms, knowledge repositories and in‑house capabilities.
• Strong understanding of tool/function calling, MCP servers, guardrails, validation, human‑in‑the‑loop patterns, observability, latency and cost optimization.
• Functional exposure to Asset Management, Investment Operations, Distribution, Client Reporting or Middle Office processes is preferred.

Roles & Responsibilities

• Lead hands‑on build, deployment and productionization of Claude based agentic AI, RAG and LLM solutions on AWS and enterprise internal platforms.
• Partner directly with business users, domain SMEs, architects, security, cloud and data teams to convert ambiguous needs into working AI products.
• Own solution design for agent workflows, API/tool integrations, prompt templates, evaluators, guardrails, human approval flows and exception handling.
• Drive rapid discovery, prototyping, MVP delivery, production hardening and scale‑up across prioritized asset management use cases.
• Provide technical leadership to FDEs and engineers through design reviews, code reviews, troubleshooting, reusable patterns and delivery governance.
• Integrate AI applications with internal systems, enterprise data sources, knowledge repositories, workflow tools and API ecosystems.
• Troubleshoot complex live issues including hallucination, retrieval quality, model behavior, latency, failed tool calls, orchestration errors and access constraints.
• Optimize performance, reliability and cost using caching, model routing, batching, prompt tuning, monitoring and architecture improvements.
• Ensure solutions align with enterprise security, IAM, encryption, audit logging, privacy, AI governance and model risk requirements.
• Create technical documentation, implementation plans, deployment runbooks, demos and transition materials for support and long‑term adoption.

Generic Managerial Skills, If any

• Strong client‑facing leadership with ability to communicate complex AI solutions clearly to business, domain, architecture and engineering stakeholders.
• Ability to lead in ambiguous environments, structure problem statements and drive fast iterative delivery with measurable outcomes.
• Strong collaboration skills across product owners, SMEs, security, cloud, data, architecture and delivery teams.
• Ownership mindset with ability to independently drive PoCs, MVPs, production fixes, technical decisions and delivery commitments.
• Strong prioritization, risk management, issue escalation and stakeholder alignment skills in live enterprise environments.
• Ability to mentor engineers, establish reusable engineering patterns, enforce code quality and promote disciplined delivery practices.

TCS Employee Benefits Summary

• Discretionary Annual Incentive.
• 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.
• Salary Range: $130,000 - 150,000 a year

Qualifications

BACHELOR OF COMPUTER SCIENCE