AI/ML Engineer (2-4 years)

JOB DESCRIPTION AI/ML Engineer (2-4 years)

Job location Bangalore/Coimbatore Work from Office 5days

Mumbai/Delhi At client's place (Depends on client's work mode)

We are seeking a passionate and skilled Senior GenAI Engineer to join our GenAI organization and contribute to ShellKode's next-generation AI initiatives.

This role focuses on building scalable GenAI and Agentic AI solutions using AWS cloud-native services, RAG architectures, and enterprise-grade orchestration workflows. The ideal candidate will have hands-on experience with LLM-based development, agentic frameworks, and AWS Bedrock.

What you will do

Design & Development

• Design and develop advanced GenAI solutions including:

• Retrieval-Augmented Generation (RAG)

• Agentic AI workflows (single-agent and multi-agent systems)

• Tool-calling and agent-to-agent orchestration

• Text-to-SQL, IDP (Intelligent Document Processing)

• Summarization, text generation, and multimodal use cases

• Build scalable GenAI services using:

• Amazon Bedrock (mandatory)

• LangChain, LangGraph, AgentCore

• Hugging Face APIs

• AWS cloud services (Lambda, API Gateway, S3, DynamoDB, Step Functions)

Engineering & Implementation

• Develop backend services and pipelines using Python (FastAPI/Flask).

• Implement embeddings, retrieval pipelines, chunking strategies, and grounding logic.

• Optimize RAG workflows, tool-calling patterns, and agentic reasoning.

• Deploy solutions using AWS-native tooling (SageMaker optional but not required for fine-tuning).

Execution & Collaboration

• Work closely with technical leads to execute assigned tasks and deliver project modules.

• Participate in requirement discussions, POCs, SOW execution, testing, and production rollout.

• Collaborate with cross-functional teams, including product owners, architects, and customer teams.

Quality, Performance & Innovation

• Monitor and improve solution robustness, latency, accuracy, and scalability.

• Implement guardrails, enterprise safety practices, and hallucination mitigation patterns.

• Stay updated on emerging LLM models, Bedrock capabilities, agent frameworks, and industry best practices.

What you will need to have

Mandatory Experience

• 2 to 4 years of overall engineering experience.

• Minimum 1 year of hands-on GenAI project experience.

• Mandatory Agentic AI experience, including:

• Multi-agent orchestration

• Tool-calling workflows

• Agent reasoning and state management

• Strong hands-on experience with AWS Cloud, including:

• Amazon Bedrock

• Lambda, API Gateway, S3, DynamoDB

• Step Functions / Event-driven architectures (preferred)

• Practical experience with:

• LangChain, LangGraph, AgentCore

• Vector databases (Pinecone, Weaviate, Chroma, Milvus)

Technical Skills

• Strong Python development experience.

• Knowledge of LLM APIs, embeddings, vector search, and RAG workflows.

• Experience building scalable backend systems and microservices.

• Familiarity with Docker, Git, CI/CD, and cloud-native deployment.

Soft Skills

• Strong analytical and problem-solving ability.

• Ability to work effectively with cross-functional teams.

• Good communication skills for customer and internal interactions.

Other Requirements

• Experience in a fast-paced startup or consulting environment is desirable.

• Prior customer-facing experience is an advantage.

• Candidates must be open to working from customer locations (onsite) when required.

• Willingness to travel occasionally for project needs