Senior AI Engineer – (Agentic Systems)

BSC Solutions India Pvt. Ltd; Bengaluru; On-site; INR 3,500,000 - 7,000,000; Full time

Job summary

BSC Solutions India Pvt. Ltd in Bengaluru seeks a Senior AI Engineer to drive production-grade GenAI systems, deploying sophisticated RAG pipelines and autonomous agent networks on AWS. You will collaborate with product, data, and DevOps teams, turning complex requirements into scalable AI software while mentoring engineers.

The role emphasizes architecture, deployment, and optimization of enterprise AI apps, with leadership in technical standards and client-facing delivery.

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering, Mathematics, Data Science, or equivalent practical experience.
• 7+ years of professional software engineering and machine learning experience in production environments.
• Demonstrated production experience building Agentic AI systems, including tool integration, autonomous reasoning, and multi-agent coordination.
• Expertise in Prompt Engineering & LLM Application Development, including structured outputs, prompt optimization, guardrails, and deterministic evaluation frameworks.
• Production experience implementing RAG architectures, vector databases (e.g., Pinecone, Milvus, Qdrant, Chroma, pgvector), chunking optimizations, and semantic retrieval.
• Advanced programming proficiency in Python, with strong command of core libraries (NumPy, Pandas, Scikit-learn) and deep learning / GenAI ecosystems.
• Hands-on experience developing conversational AI pipelines using frameworks such as LangChain, LlamaIndex, or native API orchestration.
• Practical experience deploying and managing AI/ML workloads on AWS cloud infrastructure.
• Hands-on experience building and maintaining CI/CD pipelines using GitHub Actions or Jenkins.

Responsibilities

• Architect & Deploy GenAI Solutions: design, build, benchmark, and deploy end-to-end ML and GenAI systems for real-world use cases.
• Agentic AI & Orchestration: engineer production-grade agentic workflows, autonomous agents, function calling pipelines, reflection loops, and multi-agent architectures.
• RAG Architecture: build and scale retrieval-augmented generation with semantic search and vector retrieval strategies.
• Conversational Systems: build high-throughput chatbots and interfaces using LangChain, LlamaIndex, or internal engines.
• Advanced Prompt Engineering: craft prompts with chain-of-thought, few-shot conditioning, and structured outputs to maximize determinism.
• Cloud & Infrastructure Scaling: deploy and monitor AI workloads on AWS with ECS/EKS, Lambda, SageMaker/Bedrock, CloudWatch with auto-scaling.
• CI/CD & MLOps: automate CI/CD pipelines for testing, model rollouts, and regression tracking.
• Production Reliability & Observability: establish evals, latency optimization, cost management, and tracing for reliability.
• Technical Leadership & Client Engagement: bridge client needs with engineering, mentor junior engineers in code quality and system design.
• Proven client-facing leadership: experience as a technical lead or enterprise solutions architect.
• Engineering standards & reviews: define standards, run design reviews, mentor mid-level engineers.

Skills

Generative AI

Agentic AI

Prompt engineering

LLM applications

Python

Cloud & AWS

MLOps

CI/CD

Observability

Client engagement

Education

Bachelor’s degree in CS/SE/Data Science

Tools

Pinecone

Milvus

Qdrant

Chroma

pgvector

LangChain

LlamaIndex

OpenTelemetry

TruLens

CloudWatch

Job description

About the Job

As a Senior AI Engineer, you will stand at the intersection of production systems engineering and state-of-the-art Generative AI. We are building next-generation intelligent systems that go far beyond basic text generation—transforming foundational models into autonomous, tool-using multi-agent workflows and high-performance context-aware engines.

In this role, you will own the architectural vision, deployment, and optimization of enterprise-grade AI applications. You will design robust Retrieval-Augmented Generation (RAG) pipelines, construct autonomous agent networks, build conversational systems, and harden these solutions for scale, observability, and resilience on cloud infrastructure. Working closely with product managers, data teams, DevOps, and external client stakeholders, you will translate ambiguous business requirements into high-throughput, production-ready AI software while mentoring junior engineers across the organization.

Responsibilities

• Architect & Deploy GenAI Solutions: Design, build, benchmark, and deploy end-to-end machine learning and Generative AI systems tailored to real-world enterprise use cases.
• Agentic AI & Orchestration: Engineer production-grade agentic workflows, including autonomous agents, function calling/tool-use pipelines, reflection loops, and collaborative multi-agent architectures.
• RAG Architecture: Build, evaluate, and scale Retrieval-Augmented Generation systems using semantic search, modern embedding models, and vector database retrieval strategies (chunking, hybrid search, reranking).
• Conversational Systems: Build and optimize high-throughput chatbots and conversational AI interfaces using modern LLM orchestration frameworks (LangChain, LlamaIndex, or internal engines).
• Advanced Prompt Engineering: Formulate, evaluate, and iterate systematic prompt engineering techniques (chain-of-thought, few-shot conditioning, structured outputs) to maximize output determinism and minimize hallucination.
• Cloud & Infrastructure Scaling: Deploy, scale, and monitor distributed AI workloads leveraging AWS cloud services (ECS/EKS, Lambda, Sagemaker/Bedrock, CloudWatch) with auto-scaling capabilities.
• CI/CD & MLOps: Design, automate, and maintain continuous integration and deployment pipelines (GitHub Actions, Jenkins) for seamless testing, model rollouts, and regression tracking.
• Production Reliability & Observability: Establish evaluation frameworks (evals), latency optimization, cost management, and observability tracing (e.g., OpenTelemetry, LangSmith, TruLens) for production reliability.
• Technical Leadership & Client Engagement: Serve as the technical bridge between client stakeholders and engineering, translating high-level business goals into technical architectures, and actively mentor junior engineers in code quality and system design.
• Proven track record acting as a client-facing technical lead or enterprise solutions architect.
• Experience defining engineering standards, running architectural design reviews, and mentoring mid-level and junior engineers.

Minimum Qualifications

• Bachelor’s degree in Computer Science, Software Engineering, Mathematics, Data Science, or equivalent practical experience.
• 7+ years of professional software engineering and machine learning experience in production environments.
• Demonstrated production experience building Agentic AI systems, including tool integration, autonomous reasoning, and multi-agent coordination.
• Expertise in Prompt Engineering & LLM Application Development, including structured outputs, prompt optimization, guardrails, and deterministic evaluation frameworks.
• Production experience implementing RAG architectures, vector databases (e.g., Pinecone, Milvus, Qdrant, Chroma, pgvector), chunking optimizations, and semantic retrieval.
• Advanced programming proficiency in Python, with strong command of core libraries (NumPy, Pandas, Scikit-learn) and deep learning / GenAI ecosystems.
• Hands-on experience developing conversational AI pipelines using frameworks such as LangChain, LlamaIndex, or native API orchestration.
• Practical experience deploying and managing AI/ML workloads on AWS cloud infrastructure.
• Hands-on experience building and maintaining CI/CD pipelines using GitHub Actions or Jenkins.