Lead AI & Workflow Automation Engineer

Qbotick Technologies; Bengaluru; Remote; INR 3,500,000 - 5,500,000; Full time

Benefits offered by this job

Annual learning allocation

Remote workstation hardware budget

Medical insurance coverage

Job summary

Qbotick Technologies is seeking a Lead AI & Workflow Automation Engineer for remote or Bengaluru-based work. You will architect deterministic, auditable multi-agent workflow engines and integrate enterprise-grade AI solutions with strong technical leadership.

Responsibilities include building end-to-end pipelines, RAG systems with vector databases, and monitoring/observability for high reliability. The role requires 6+ years in backend engineering with NLP/LLM experience and proficiency in

Qualifications

• 6+ years backend engineering with at least 3 years focused on production NLP/LLM orchestration.
• Proficiency with Python, TypeScript, LangChain/LlamaIndex, and distributed queue systems (Celery, BullMQ).
• Experience deploying models with high availability, rate limiting, and observability.
• Familiarity with compliant AI decision systems in regulated contexts is a plus.

Responsibilities

• Design enterprise autonomous agent pipelines with deterministic state machines and strict human-in-the-loop controls.
• Implement robust RAG pipelines with vector databases (Pinecone, Qdrant, pgvector) and hybrid semantic search.
• Develop structured evaluation frameworks benchmarking token economics, latency, and model output determinism.
• Ensure zero-data-leakage enterprise privacy protocols when interfacing with foundation model APIs.
• Build real-time monitoring and fallback systems for automated decision pipelines.

Skills

Python

TypeScript

NLP/LLM orchestration

Distributed systems

AI/Automation architecture

Tools

LangChain/LlamaIndex

Celery

BullMQ

Pinecone

Qdrant

pgvector

API integrations

Job description

Artificial Intelligence & Automation staff Engineering Remote / Bengaluru, India Full-Time

Lead AI & Workflow Automation Engineer

Architect deterministic, auditable multi-agent workflow engines and machine intelligence integrations for enterprise operations requiring high reliability.

In this role, you will be directly responsible for system correctness, operational stability, and technical leadership across the following dimensions:

• Design enterprise autonomous agent pipelines with deterministic state machines and strict human-in-the-loop controls.
• Implement robust RAG pipelines with vector databases (Pinecone, Qdrant, pgvector) and hybrid semantic search.
• Develop structured evaluation frameworks benchmarking token economics, latency, and model output determinism.
• Ensure zero-data-leakage enterprise privacy protocols when interfacing with foundation model APIs.
• Build real-time monitoring and fallback systems for automated decision pipelines.

We evaluate candidates against demonstrated systems experience and sound foundational thinking:

• 6+ years in backend engineering with at least 3 years focused on production NLP/LLM orchestration.
• Proficiency with Python, TypeScript, LangChain/LlamaIndex, and distributed queue systems (Celery, BullMQ).
• Firm understanding of prompt engineering architectures, token budgets, and embeddings vectorization.
• Experience deploying models with high availability, rate limiting, and observability.

Preferred / Nice-to-Have Background

• Hands-on experience fine-tuning open models (Llama, Mistral) on domain-specific datasets.
• Familiarity with compliance standards for AI decision systems in regulated sectors.

Compensation & Work Model

Competitive Enterprise Band + Distributed Equity Grant aligned with high-performance engineering benchmarks. Every role includes an annual learning allocation, remote workstation hardware budget, and medical insurance coverage.

Benefits & Support

Designed for Deep Engineering Work

We provide the tooling, flexibility, and financial stability necessary to focus on high-impact software systems.

Top-Tier Workstation Setup

High-spec Apple Silicon or Linux workstation of your choice plus a dedicated 4K display and ergonomic home-office stipend.

Annual budget for technical books, cloud certifications (AWS/GCP/CKA), research papers, and technical conference attendance.

Engineers control their calendar with protected focus blocks. We measure outputs and system uptime, not seat time.

Premium medical and hospitalization insurance coverage for team members, spouses, and dependent children.

Transparent Compensation

Senior market-rate compensation structures with transparent evaluation criteria and long-term equity participation.

Generous Leave & Sabbaticals

Encouraged paid time off, national holidays, and extended sabbatical opportunities to prevent burnout and recharge.

Open Technical Inquiries

Don't See Your Specific Specialty?

We are always interested in speaking with exceptional systems engineers, compilers/runtime researchers, and security architects. Reach out with your portfolio or technical writings.