SHIVAM(1)Portfolio ManualSHIVAM(1)
NAME
shivam — product & technology leader for AI-native software
SYNOPSIS
shivam [--strategy] [--architecture] [--delivery] [--teams] idea → production
DESCRIPTION
13+ years across software delivery, technical training, data and AI consulting, and product leadership. Since 2019 I have led product and engineering for AI hiring systems: skills assessments, candidate screening, and conversational interviews.
OPTIONS
--strategy
From customer discovery to a roadmap the business can commit to.
customer and requirement discovery, brds and prds, prioritisation and roadmap shaping, 0-to-1 product development
--architecture
Direction for AI systems that have to survive production load.
architecture direction, rag pipelines and llm orchestration, agent-based automation, cloud microservices on aws
--delivery
Turning demos into rollouts, and rollouts into adoption.
release planning, requirement workshops and demos, client-facing rollout, escalation handling
--teams
Building the people and operating rhythm behind the product.
helped build and scale the india operation, team building and mentoring, delivery governance, cross-functional coordination
SYSTEMS
Enterprise Skills Assessment Platform● production · evaluation
Skills evaluation for enterprise hiring teams: coding and data-science tests, source-code verification, remote proctoring, and analytics across a 500+ skill library.
$ trace skills-assessment-platform
Skill library ─▶ Candidate attempt ─▶ Proctoring signals ─▶ Code verification ─▶ Analytics
# role: Product and technology leadership — discovery, prioritisation, architecture direction, release planning, rollout.
AI-Assisted Candidate Screening● production · screening
A recruiter-facing assistant combining embedding search and LLM ranking for JD–CV matching, context-aware question generation, and structured candidate reports.
$ trace candidate-screening-assistant
Résumés + JD ─▶ Parsing ─▶ Embedding search ─▶ LLM ranking ─▶ Questions + report
# role: Built the RAG-based assistant and deployed it with enterprise clients.
Conversational Interviewing System● production · interview
An agentic interview system running multi-turn conversations with dynamic follow-ups, live coding support, identity controls, and LLM-generated insights for reviewers.
$ trace conversational-interviews
Candidate answer ─▶ Agentic interviewer ─▶ Follow-up or code task ─▶ Signals for review ─▶ Reviewer insights
# role: Architected the agentic interview flow and led productisation.
ARCHITECTURE
┌ L5 Experience Recruiter assistant · Assessments · Conversational interviews · Reporting ┌ L4 Orchestration Agentic workflows · LLM orchestration · Multi-turn flows ┌ L3 Intelligence LLMs · NLP · Prompt engineering · Classification ┌ L2 Retrieval & data Embeddings · Vector search · Résumé parsing · Analytics ┌ L1 Platform Microservices · REST APIs · Containers · Serverless
HISTORY
$ git log --oneline --decorate career
9f3a2c (HEAD -> main) Product & engineering leadership · Head of Product @ Otomeyt AI · Apr 2019–Present
AI hiring technology. End-to-end product thinking with hands-on AI system design.
9f1eaf Big Data & AI Consultant @ Paness IIHT · Jul 2017–Oct 2018
AI/ML consulting: chatbots, data mining, and analytics-led business support for clients.
9f0332 Technical Manager @ ASIT · Apr 2014–Jul 2017
Helped initiate a software-development division and managed delivery of new initiatives.
9ee7b5 Independent Developer & Trainer @ Self-employed · Aug 2013–Mar 2014
Built college-level software projects and trained students on development practices.
9ecc38 Technical Trainer @ NIIT · Aug 2012–Aug 2013
Technical training for freshers and working professionals.
EXIT STATUS
0 PoC to production — Converted multiple proofs of concept into enterprise-scale features used in high-volume hiring workflows.
0 AI-native platform — Embedded agentic workflows and LLM decision layers across screening, assessments, and interviews.
0 Scaled an operation — Helped build and scale the India operation, partnering on product direction and execution priorities.
0 Started a division — Helped initiate a software-development division and delivered its first initiatives.
FILES
$ ls -la ./lab # 15+ proofs of concept; selected areas
| drwxr-xr-x | production | document ai | r-sum-intelligence/ |
| drwxr-xr-x | production | retrieval | semantic-jd-cv-matching/ |
| drwxr-xr-x | production | llms | llm-ranking-and-shortlist-reasoning/ |
| drwxr-xr-x | production | generation | context-aware-question-generation/ |
| drwxr-xr-x | production | generation | structured-candidate-reports/ |
| drwxr-xr-x | production | code ai | source-code-analysis-and-evaluation/ |
| drwxr-xr-x | production | vision | video-analytics-for-assessments/ |
| drwxr-xr-x | production | agents | agentic-interview-orchestration/ |
| drwxr-xr-x | developed | speech + llms | written-and-spoken-answer-evaluation/ |
| drwxr-xr-x | research | voice | real-time-voice-turn-latency/ |
| drwxr-xr-x | client delivery | conversational ai | enterprise-chatbots/ |
| drwxr-xr-x | client delivery | analytics | data-mining-and-decision-support/ |
NOTES
1. Workflow fit before model cleverness. An AI feature can win the demo and still fail in daily use. I judge it by whether it makes someone’s work meaningfully easier.
2. Prove it small, then productise. Validate as a proof of concept before committing a roadmap; carry what holds up into production.
3. Platform judgement. Know when to build a reusable capability and when to deliver a targeted customisation for an enterprise account.
SEE ALSO
Accuracy alone doesn’t drive adoption. Workflow fit does. (Feb 2026)
AI will change things in ways people don’t expect. (Mar 2026)
I asked AI the question everyone is quietly thinking. (Sep 2026)
AUTHOR
Shivam Mishra, Bengaluru, India. Reach me on LinkedIn.
Titles are descriptive; employer-built systems belong to their employers.