Sr. AI Engineer (Agentic AI & LLM Systems) #Remote #7+ years

Job Title: Sr. AI Engineer (Agentic AI & LLM Systems)

Company: NetAnalytiks Technologies Ltd. (Hiring for Beroe Inc.)

Location: Remote, India (Shortlisted candidates must attend a face-to-face discussion in Bangalore or Chennai)

Work Mode: Remote

Experience: 7+ years Start

Date: Immediate or Short Notice

About Beroe Inc. Beroe Inc. is a global leader in procurement intelligence and analytics, empowering businesses with actionable insights to optimize sourcing strategies. We are building next-generation AI-driven solutions to transform procurement and supply chain processes. Role Overview We are seeking an AI Engineer with deep expertise in Agentic AI systems and LLM-based architectures. This is a hands-on role focused on designing and deploying intelligent multi-agent workflows, retrieval-augmented generation (RAG) pipelines, and fine-tuned LLMs for real-world business applications.

Key Responsibilities

Design and implement agentic AI pipelines using LangGraph, LangChain, CrewAI, or custom frameworks.

Build robust RAG systems with vector databases (FAISS, Pinecone, OpenSearch).

Fine-tune, evaluate, and deploy LLMs for task-specific applications.

Integrate external tools and APIs into multi-agent workflows using dynamic tool/function calling. Develop memory modules (short-term context, episodic memory, long-term vector stores).

Build scalable, cloud-native services using Python, Docker, and Terraform.

Collaborate in agile, cross-functional teams to prototype and ship ML-based features.

Monitor and evaluate agent performance using tailored metrics (success rate, hallucination rate). Ensure secure, reliable, and maintainable deployment of AI systems in production.

Required Qualifications

7+ years of experience in Machine Learning, NLP, or Software Engineering.

Strong proficiency in Python and ML libraries (PyTorch, TensorFlow, scikit-learn, XGBoost).

Hands-on experience with LLMs (GPT, Claude, LLaMA, Mistral) and NLP tooling (LangChain, HuggingFace, Transformers).

Expertise in RAG pipelines, semantic search, and reranking.

Familiarity with agent frameworks and orchestration techniques.

Deep understanding of prompt engineering, embeddings, and LLM architecture basics.

Solid foundation in microservice architectures, CI/CD, and Infrastructure-as-Code (Terraform).

Experience integrating REST/GraphQL APIs into ML workflows.

Bonus Skills

Experience with RLHF, LoRA, or parameter-efficient LLM fine-tuning.

Familiarity with CrewAI, AutoGen, Swarm, or other multi-agent libraries.

Exposure to cognitive architectures (task trees, state machines, episodic memory).

Awareness of AI security risks (prompt injection, data exposure).

Education Engineering Graduate with relevant experience in AI/ML/NLP.