Job Description
Bestpeers InfoSystem Pvt. Ltd. is looking for an experienced AI/ML Engineer to design,
develop, and deploy production-grade AI solutions across Agentic AI, Retrieval-Augmented
Generation (RAG), Large Language Models (LLMs), Natural Language Processing (NLP), and
Computer Vision.
The ideal candidate will have strong Python programming skills, hands-on experience with
modern AI architectures, and a proven ability to build scalable, secure, and reliable AI systems
for real-world business applications.
Responsibilities
- Design, fine-tune, and deploy Machine Learning, NLP, LLM, and Computer Vision
solutions for business use cases. - Develop agentic and multi-agent AI systems with tool calling, planning, orchestration,
memory, guardrails, and human-in-the-loop workflows. - Build and optimize RAG pipelines, including data ingestion, chunking, embeddings,
retrieval, re-ranking, and grounded generation. - Fine-tune LLMs when measurable improvements justify fine-tuning over prompting or
RAG-based approaches. - Develop Computer Vision pipelines for image classification, object detection, OCR, and
video analytics. - Deploy and serve AI models and agents in production while optimizing latency, reliability,
scalability, and cost. - Build evaluation frameworks to identify hallucinations, retrieval failures, and model
accuracy degradation. - Integrate vector databases and knowledge graphs to support efficient information
retrieval and reasoning. - Implement production monitoring and tracing across model inference, retrieval pipelines,
and agent execution. - Apply AI governance and security practices, including data protection, access control,
prompt-injection defense, and auditability. - Collaborate with Data Science, Engineering, Product, and Compliance teams to deliver
business-focused AI solutions.
Required Skills & Qualifications
- Strong Python programming and software engineering fundamentals, including writing
clean, tested, and maintainable code. Python is mandatory. - Proficiency in at least one backend framework: Flask, Django, or FastAPI.
- 3+ years of experience in AI/ML engineering, including real-world production
deployments. - Practical experience developing and deploying NLP and LLM-powered applications.
- Hands-on experience with LLM fine-tuning.
- Experience building agentic AI or multi-agent systems.
- Strong understanding of RAG architectures, retrieval optimization, embeddings, and
vector databases. - Practical experience developing Computer Vision pipelines.
- Experience designing evaluation frameworks for ML models, RAG systems, or AI
agents. - Working knowledge of REST APIs, SQL, Docker, Git, CI/CD, and MLOps practices.
- Experience deploying AI/ML workloads on at least one major cloud platform: AWS, GCP,
or Azure. - Understanding of production requirements, including latency, scalability, reliability,
security, and cost optimization.
Good to Have
- Knowledge of graph databases and knowledge graph technologies such as Neo4j.
- Experience with distributed, multimodal, or real-time AI systems.
- Familiarity with Kubernetes, GPU-based workloads, and model-serving infrastructure.
- Experience working in regulated industries such as finance, healthcare, or insurance.
What We’re Looking For
- Strong analytical thinking and problem-solving abilities.
- Ability to translate business requirements into scalable AI solutions.
- A practical, production-focused approach to AI engineering.
- Strong collaboration and communication skills.
- A commitment to continuous learning and staying current with evolving AI technologies.
Experience Required:
3+ Years
Note: Candidates should have hands-on production experience in AI/ML engineering, with
practical expertise in Python, LLM fine-tuning, Agentic AI, RAG, and Computer Vision.