AI Systems & Conversational Intelligence Architect

Weekday (YC W21); Bengaluru; On-site; INR 1,500,000 - 3,000,000; Full time

Benefits offered by this job

Ownership of AI systems

Growth opportunities in AI

Collaboration with cross-functional teams

Job summary

A dynamic technology client based in Bengaluru is looking for a skilled professional to design and deploy scalable conversational AI systems. The role demands over 5 years of experience in machine learning and natural language processing, with strong expertise in Python. Candidates should be proficient in tools like PyTorch and Docker. This is a full-time opportunity offering engaging challenges in AI technologies with significant ownership and growth potential.

Qualifications

• 5+ years of experience in building and deploying ML or NLP systems.
• Strong Python expertise with hands-on experience in ML tooling.
• Proven experience designing scalable conversational systems.

Responsibilities

• Design scalable multi-turn conversational systems and orchestration layers.
• Architect embedding-based search systems and dynamic re-ranking strategies.
• Deploy open-source and proprietary LLMs in low-latency environments.

Skills

Python expertise

Machine Learning (ML)

Natural Language Processing (NLP)

Scalable conversational AI

Experience with distributed systems

Tools

PyTorch

scikit-learn

HuggingFace

Docker

Job description

Job Overview

This role is for one of our clients.

Industry: Technology, Information and Internet

Seniority level: Mid-Senior level

Min Experience: 5 years

Location: Bangalore

Job type: full-time

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.

Key Responsibilities

• Conversational Architecture & LLM Orchestration
  • Design scalable multi‑turn conversational systems with contextual memory and adaptive personalization.
  • Build orchestration layers that manage prompts, routing logic, fallback strategies, and multi‑model interactions.
  • Develop automated evaluation pipelines to measure response accuracy, factual consistency, tone alignment, and hallucination mitigation.
  • Optimize latency, throughput, and cost efficiency through batching, caching, and architectural refinements.
• Retrieval & Context Engineering
  • Architect embedding‑based search systems and vector retrieval pipelines.
  • Design end‑to‑end retrieval‑augmented generation (RAG) workflows integrating structured and unstructured knowledge sources.
  • Improve contextual reasoning by combining semantic search, metadata filtering, and dynamic re‑ranking strategies.
• Personalization & Applied ML Systems
  • Build intelligent ranking, recommendation, and user segmentation pipelines.
  • Develop adaptive content generation systems tailored to user preferences and behavioral signals.
  • Fine‑tune and adapt multilingual NLP/NLG systems, including support for Hindi and other regional languages.
• Model Optimization & Production Deployment
  • Deploy open‑source and proprietary LLMs in scalable, low‑latency environments.
  • Evaluate trade‑offs between performance, cost, and model complexity.
  • Implement MLOps best practices including versioning, monitoring, automated evaluation, and continuous improvement workflows.
  • Design cloud‑native AI systems leveraging distributed compute, storage, and caching infrastructure (AWS preferred).
• Workflow Automation & Infrastructure
  • Build robust ML pipelines using orchestration frameworks such as Airflow, Prefect, or Celery.
  • Integrate modern data stack components including relational databases, caching layers, object storage, and streaming systems.
  • Containerize and deploy services using Docker and scalable infrastructure patterns.

Candidate Profile

• Required Experience
  • 5+ years of experience building and deploying ML or NLP systems in production environments.
  • Strong Python expertise with hands‑on experience in PyTorch, scikit‑learn, HuggingFace, and LLM tooling ecosystems.
  • Demonstrated experience with embeddings, vector search systems, and RAG pipelines.
  • Proven ability to design scalable conversational AI systems with dialog management and context handling.
  • Strong understanding of distributed system design and cloud‑based deployments.
• Preferred Experience
  • Experience developing multilingual conversational agents or recommendation systems.
  • Exposure to advanced fine‑tuning methods such as LoRA, PEFT, RLHF, or prompt optimization strategies.
  • Contributions to open‑source AI/LLM projects.
  • Experience working on culturally nuanced or content‑rich AI applications.

What You’ll Gain

• Ownership of foundational AI systems shaping large‑scale conversational experiences.
• Opportunity to solve complex multilingual and personalization challenges using frontier LLM technologies.
• Collaboration with cross‑functional teams spanning product, engineering, and domain expertise.
• Long‑term growth opportunities in AI architecture and platform leadership.

Core Competencies

• Large Language Models
• Retrieval‑Augmented Generation
• Multilingual NLP
• Personalization Systems
• Vector Search
• Model Deployment
• MLOps
• Cloud‑Native AI Infrastructure
• Scalable ML Engineering