Haystack
โ† Back to Jobs
Full time
Other
WA

Agentic AI

Weekday AIPune, Maharashtra๐Ÿ‡ฎ๐Ÿ‡ณIndiaPosted 16 Sept 2026

Quick Overview

Seniority
Mid Senior
Employment type
Full Time
Work mode
On Site
Location
Pune, Maharashtra, India
Posted
5 days ago
Machine LearningGenerative AILLMPandasPython

Job Description

๐—ง๐—ต๐—ถ๐˜€ ๐—ฟ๐—ผ๐—น๐—ฒ ๐—ถ๐˜€ ๐—ณ๐—ผ๐—ฟ ๐—ผ๐—ป๐—ฒ ๐—ผ๐—ณ ๐˜๐—ต๐—ฒ ๐—ช๐—ฒ๐—ฒ๐—ธ๐—ฑ๐—ฎ๐˜†'๐˜€ ๐—ฐ๐—น๐—ถ๐—ฒ๐—ป๐˜๐˜€

๐—ฆ๐—ฎ๐—น๐—ฎ๐—ฟ๐˜† ๐—ฟ๐—ฎ๐—ป๐—ด๐—ฒ: ๐—ฅ๐˜€ ๐Ÿฏ๐Ÿฌ๐Ÿฌ๐Ÿฌ๐Ÿฌ๐Ÿฌ - ๐—ฅ๐˜€ ๐Ÿฎ๐Ÿฒ๐Ÿฌ๐Ÿฌ๐Ÿฌ๐Ÿฌ๐Ÿฌ (๐—ถ๐—ฒ ๐—œ๐—ก๐—ฅ ๐Ÿฏ-๐Ÿฎ๐Ÿฒ ๐—Ÿ๐—ฃ๐—”)

Experience: 3+ yrs

Location: Pune

Job Type: Full-time

We are looking for an experiencedย AI/ML Engineerย with strong expertise inย Machine Learning, Large Language Models (LLMs), Small Language Models (SLMs), LangChain, and LangGraph. The role focuses on designing, developing, training, evaluating, and deploying intelligent AI solutions using modern machine learning and generative AI technologies.

The ideal candidate will have strong Python programming skills, hands-on experience with supervised and unsupervised learning, and a solid understanding of responsible AI, explainability, model safety, and controlled generation.

KEY RESPONSIBILITIES

  • Design, develop, and implementย machine learning and generative AI solutionsย using LLMs and SLMs.
  • Build AI workflows and agentic applications usingย LangChain and LangGraph.
  • Apply supervised and unsupervised learning techniques to solve business and technical problems.
  • Prepare, process, analyse, and transform datasets usingย Python and dataframe-centric processing.
  • Train, fine-tune, validate, and evaluate machine learning and language models.
  • Develop model evaluation frameworks and establish appropriate performance and quality metrics.
  • Experiment with different model architectures, prompts, parameters, and optimisation techniques.
  • Implementย Explainable AI (XAI)ย approaches to improve model transparency and interpretability.
  • Applyย Responsible AI principlesย throughout model development and deployment.
  • Design and implement AI guardrails, safety mechanisms, and controlled-generation techniques.
  • Identify and mitigate risks related to hallucination, unsafe outputs, bias, and unreliable model behaviour.
  • Develop reliable AI pipelines that support experimentation, evaluation, and production use cases.
  • Collaborate with engineering, data, product, and business teams to translate requirements into practical AI solutions.
  • Troubleshoot model, data, pipeline, and inference-related issues and continuously improve system performance.
  • Stay current with developments inย LLMs, SLMs, agentic AI, machine learning, AI safety, and responsible AI.

WHAT MAKES YOU A GREAT FIT

  • 3+ years of professional experienceย in Machine Learning, AI/ML Engineering, Data Science, or a related field.
  • Strong hands-on experience withย Machine Learning, LLMs, and SLMs.
  • Mandatory experience with LangChain and LangGraph.
  • Strong understanding of supervised and unsupervised machine learning techniques.
  • Hands-on experience withย model training, fine-tuning, tuning, validation, and evaluation.
  • Advanced proficiency inย Pythonย and data-centric programming.
  • Strong experience working withย Pandas or comparable dataframe-based data-processing frameworks.
  • Understanding of LLM application development, prompt engineering, inference workflows, and model optimisation.
  • Practical knowledge ofย Explainable AI (XAI)ย and model interpretability techniques.
  • Strong understanding ofย Responsible AI, AI governance, and ethical model-development practices.
  • Experience implementingย AI guardrails, safety controls, content filtering, and controlled-generation techniques.
  • Strong analytical and problem-solving skills with the ability to experiment, evaluate, and iterate on AI solutions.
  • Ability to work effectively with cross-functional engineering, data, product, and business teams.
  • Strong communication skills and the ability to clearly document technical approaches, model behaviour, and evaluation results.

Similar jobs