Principal AI Engineer (Voice Bot, Agentic AI)
Overview
This is a foundational role blending applied machine learning, LLM integration, and modern data engineering to drive real-time decisioning and automation. The principal engineer will lead implementation of LLM-based features, fine-tune models for vernacular languages, build LangChain pipelines, and deploy inference with FastAPI, Docker, and Kubernetes. They will also integrate AI into core product features like Dialer, CRM sync, and IVR, and architect scalable data pipelines.
What You'll Do7
- 1Lead implementation of LLM-based features: summarization, sentiment detection, auto-disposition, escalation tagging
- 2Fine-tune and evaluate models (Whisper, GPT, HuggingFace, Rasa) for vernacular (Indian) language support
- 3Build and deploy LangChain pipelines for prompt engineering, QA tagging, and agent assist
- 4Prototype emotion recognition, contextual agent replies, and real-time assist layer
- 5Build and maintain inference pipelines using FastAPI, Docker, Kubernetes
- 6Optimize model latency and deployment strategy for high concurrency environments
- 7Architect scalable data pipelines using PostgreSQL, Redis, and Kafka
Requirements7
- 1Total experience of 8-15 years with Agentic AI and Voice Bot development experience mandatory
- 2Minimum 5 years of experience in AI with exposure to LLMs and production-grade pipelines
- 3Hands-on with Whisper, LangChain, HuggingFace, or similar frameworks
- 4Solid Python (FastAPI preferred), SQL/PostgreSQL, and experience with RESTful APIs
- 5Proven experience with CI/CD, Docker, K3s/Kubernetes, Redis, Kafka/RabbitMQ
- 6Strong understanding of NLP/STT/TTS, summarization, and emotion tagging
- 7Ability to work in startup-paced environments with ownership mindset
Who Should Apply
The ideal candidate is an experienced AI engineer with 8-15 years in AI and mandatory experience in Agentic AI and Voice Bot development. They have deep hands-on expertise with LLMs, LangChain, Whisper, and HuggingFace, and proficiency in Python (FastAPI), PostgreSQL, and containerization tools (Docker, Kubernetes). They are comfortable in a startup-paced environment, take ownership, and have strong NLP/STT/TTS understanding.
Salary Insight
Open to discussion
Location
Required Skills
Application Tip
Highlight your experience with Agentic AI and Voice Bot projects, especially deploying production-grade pipelines using LangChain and FastAPI.
See NearSkill jobs more often in your search
How your application is processed
1Application received
Your resume and details are logged the moment you apply.
2ATS + eligibility screening
We check your profile against the role’s skills, seniority, and requirements.
3Employer sees qualified profiles only
Only candidates who clear screening move forward.
Similar open positions
Explore active roles that match your skills and interests.
Talentxo
VerifiedAl/ML Engineer
We are looking for a hands-on AI/ML Engineer to build and deploy intelligent AI solutions across a communication platform. The role involves developing LLM-powered applications, voice AI capabilities, NLP pipelines, and production-grade ML systems that enable automation and real-time decision-making.
Turing
VerifiedSenior LLM Engineer
A remote role based in India centers on designing and building Generative AI and LLM systems with Python and Langchain. The engineer will create RAG pipelines, prompt techniques, and agent-based workflows that run in production. The position expects 7-12 years of experience and close work with engineering teams, business SMEs, and data teams to shape the LLM roadmap. Strong SQL and cloud familiarity across AWS, Azure, or GCP support the day-to-day work.
Talentxo
VerifiedAI Solutions Engineer (GenAI & Full Stack)
This role focuses on designing, developing, and deploying AI-powered applications using Large Language Models (LLMs) such as GPT, Claude, Gemini, and LLaMA. The position requires full-stack development with Python backend and React.js frontend, along with expertise in prompt engineering and RAG. The engineer will build scalable cloud-native solutions on AWS or GCP and collaborate with cross-functional teams.
Micro1
VerifiedAi Ml Engineer for Internal Platforms Remote
Remote role building and refining an AI recruiting agent with production-ready features. You’ll push newer capabilities, test cutting edge LLMs and agent frameworks, and deploy AI-powered services that improve reliability and usefulness. Expect collaboration with product and engineering to ship tangible enhancements. You will work on backend Python services and keep pace with evolving AI tools and practices. Bold technologies: Python, LLMs, LangChain and AWS.</br>
Talentxo
VerifiedData Scientist / AI Engineer (Python, ML, RAG)
The candidate will own the end-to-end development of AI powered applications at scale. They will work on Retrieval-Augmented Generation pipelines and semantic search over structured and unstructured data. The role involves building and deploying RESTful APIs for NLP models, integrating LLMs and SLMs, and monitoring model performance in production. The team uses Python based backends, FastAPI or Flask, and vector databases such as FAISS or Pinecone to enable advanced NLP capabilities. What makes this role different is the emphasis on production grade MLOps, high volume APIs, and cross-functional collaboration within financial services contexts.
Talentxo
VerifiedSenior Backend Engineer (Node.js, AI-Native)
This role is for a Senior Backend Engineer to build core Node.js services and REST APIs from scratch, owning system design end to end. You will ship AI/ML-powered features including LLM and agentic capabilities, and use AI-native tooling across the development lifecycle.