AI Agentic Engineer

Must Have Technical / Functional Skills

* Core Engineering & Programming:
Strong software engineering fundamentals with expert-level proficiency in Python.

Experience with Java, Go, or Type Script is a strong plus.

* LLM & GenAI Application Development:
Proven, hands-on experience building and deploying production-grade applications using Large Language Models (LLMs) like GPT, Claude, or Gemini.

* This must go beyond simple API calls and include experience with tool/function-calling, structured outputs, and evaluation.

* Agentic AI Frameworks & Orchestration:
Demonstrable expertise in designing and implementing agentic workflows using frameworks like Lang Graph, Semantic Kernel, Auto Gen, or similar.

* Experience with multi-agent systems, planning, and autonomous execution is critical.

* RAG (Retrieval-Augmented Generation):
Deep, practical knowledge of building and optimizing RAG pipelines. This includes data ingestion, various chunking strategies, embeddings, vector databases (e.g., Pinecone, Chroma, FAISS), and hybrid search/reranking.

* Production & MLOps:

Experience with production engineering practices, including building scalable APIs (REST, RPC), microservices, CI/CD pipelines, containerization (Docker, Kubernetes), and cloud platforms (AWS, Azure, or GCP).

Roles & Responsibilities

* Agentic System Design & Engineering:
Architect, build, and deploy advanced AI agents capable of autonomous reasoning, decision-making, and self-directed task execution. Design and implement complex, multi-step agentic workflows that integrate with enterprise APIs, data sources, and platforms.

* RAG and Grounding Implementation:
Develop robust RAG pipelines to ground agent responses in factual, reliable data. This includes managing the full lifecycle from data ingestion and vectorization to retrieval and citation.

* Tooling and Integration:
Build and maintain the "tools" that agents use to interact with the digital world. Create secure, well-documented tool interfaces for internal services, databases, and third-party APIs.

* Evaluation, Guardrails & Safety:
Design and implement comprehensive evaluation frameworks to measure agent performance, accuracy, and reliability.

* Develop and enforce safety guardrails, policy checks, and fallback mechanisms to ensure agents operate safely and predictably in production environments.

* Optimization and Productionization:
Debug, monitor, and optimize agentic systems for latency, cost, and efficiency. Own the end-to-end deployment process, including CI/CD, structured logging, and incident response for AI systems.

Generic Managerial Skills, If any

* Problem-Solving & Critical Thinking:
Ability to analyze complex, ambiguous problems and design innovative, practical solutions. Thrives in navigating the uncertainty inherent in emerging AI technologies.

* Collaboration & Communication:
Excellent communication skills with the ability to articulate complex technical concepts to both technical and non-technical stakeholders. Proven experience working cross-functionally with product, research, and infrastructure teams.

* Ownership & Leadership: A bias for action and a strong sense of ownership. Capable of driving projects from conception to completion, mentoring junior engineers, and helping to define and influence AI strategy and best practices

Base Salary Range : $100,000 to $120,000 Per Annum

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.

#LI-SV2

#LI-KUMARAN