Industries we serve
Secure, compliant platforms for banking, fintech, and wealth management where downtime is not an option.
Revenue intelligence, booking systems, and high-touch digital experiences for premium travel brands.
Adaptive learning platforms, LMS infrastructure, and AI-powered content operations for global institutions.
Smart property platforms, resident applications, and ESG reporting tools for the built environment.
ERP modernization, process automation, and data platforms that enable large organizations to operate with speed, control, and global scale.
Environmental impact tracking, ESG reporting infrastructure, and compliance platforms for responsible organizations.
Content platforms, streaming infrastructure, and monetization systems built to scale audience engagement and performance.
Engineering
Posted January 15, 2025
Salary
Competitive, based on experience and location
Location
Coimbatore
From autonomous hiring agents to intelligent video tutors to end-to-end LLM-powered workflows — we build systems where AI doesn’t just assist — it acts.
What You’ll Build
You’ll work on bleeding-edge LLM pipelines that integrate:
LangChain, CrewAI, and n8n to orchestrate reasoning, memory, and workflows
LLMs (GPT-4, Claude, Ollama) to generate scripts, analyze visuals, and drive decision-making
Vision APIs (OpenAI Vision, Google Vision) to parse images, diagrams, UIs, or screenshots
Video Avatar Generation using tools like D-ID, Synthesia, or open-source alternatives
TTS Engines like ElevenLabs, PlayHT, or Bark for ultra-realistic speech
Custom pipelines where avatars can SEE → THINK → TALK
Stack You’ll Touch
LangChain, CrewAI, n8n
GPT-4, Claude, Ollama (running LLMs locally)
OpenAI Vision, Google Vision, Claude with images
ElevenLabs, Bark, PlayHT, D-ID, Wav2Lip, FaceSwap
FastAPI, Python, MongoDB, PostgreSQL, Docker
Vector DBs: Chroma, Pinecone, Weaviate
Must Have
Minimum 2 years of experience building with LLM APIs and chaining tools (LangChain or equivalent)
Hands-on work with Vision APIs or image-to-text prompts (show us something)
Python fluency — especially async, APIs, and data manipulation
Hunger to automate, integrate, and own features
The audacity to debug anything and the curiosity to ask “What if this could talk?”
Bonus Points For
Ran Ollama or other open-source LLMs locally
Used D-ID, Wav2Lip, or generated avatar videos from text
Experience wiring together agents with tools/memory/RAG
Public GitHub projects, startup experience, or shipped AI products
Who This Is Not For
Students looking to “learn slowly” — we’ll move faster than your comfort zone
People waiting for Jira tickets — we expect you to own the problem, not just the task
Those afraid to write ugly code to prove the concept — we clean up after velocity
Why Incresco?
You’ll ship features that go live in days, not quarters
You’ll work directly with founders, not middle managers
We invest in builders who think like hackers and execute like founders
Location: Bangalore
Mode: WFO
We care more about the quality of your work and thinking than specific degrees. A strong track record in similar roles matters most.
We aim to complete the entire process within 5 days, depending on everyone's availability. We prefer in-person discussions as much as possible to get to know each other better and ensure a mutual fit.
Apply For This Position