Skit.ai is a pioneer in Conversational AI, transforming the collections ecosystem through omnichannel, GenAI-powered assistants. Skit.ais Collection Orchestration Platform the worlds first of its kind streamlines and synchronizes collection conversations across channels and accounts.

At the core of this platform is Skit.ais Large Collection Model (LCM), a domain-specific LLM designed to optimize collection strategies, improve customer experience, and drive measurable business outcomes for enterprises.

Role Overview :

Job Title : Forward Deployed AI Engineer

Location : Bangalore (100% Work From Office)

Experience : 3 - 4 years

Employment Type : Full-time

Mission :

You are part of Skit.ais Special Forces the team that bridges core AI research with real-world client deployments. This role goes far beyond prompt engineering or configuration. You will architect, deploy, and own AI systems in complex enterprise environments, ensuring production-grade performance and measurable impact.

Tech Stack & Core Expertise :

- Python

- Large Language Model (LLM) architecture patterns

- Automatic Speech Recognition (ASR) & Text-to-Speech (TTS) systems

- Retrieval-Augmented Generation (RAG)

- Conversational AI deployment at scale

Key Responsibilities :

1. Architecture & System Design :

- Design end-to-end AI solutions - not just prompts or workflows

- Deeply understand LLM capabilities, limitations, and failure modes

- Create scalable training data templates and conversation structures

- Design and implement RAG pipelines, particularly for the banking and collections domain

2. Deep AI Configuration & Optimization :

- Tune ASR endpointing configurations for real-world call conditions

- Configure and optimize VAD (Voice Activity Detection) thresholds

- Adjust TTS prosody, pacing, and tone based on business use cases

- Go beyond language setup to ensure production-grade conversational quality

3. Deployment & Integration :

- Write robust Python integration code

- Integrate conversational AI systems into banking and enterprise workflows

- Work closely with client teams to align AI behavior with business logic

- Own bot performance end-to-end, from deployment to continuous optimization

Requirements :

- 3 - 4 years of experience in AI/ML deployment or applied AI engineering

- Strong hands-on Python programming skills

- Solid understanding of LLM architectures, constraints, and real-world behavior

- Experience configuring and tuning ASR and TTS systems

- Hands-on experience implementing RAG-based solutions

- Strong client-facing communication and technical articulation skills

- Highly self-directed problem solver with ownership mindset